AI Agents and Claude Automation. Built With a Person in the Loop.
We build and run AI agents on Claude that read your messages and documents, use your tools and finish multi-step jobs, with approval points where a person decides and logs you can read. We use Claude Code where it fits to build internal tools and integrations quickly, and write the CLAUDE.md files that make agents follow your company's rules.
What an AI Agent Does That a Script Does Not
Devvista is a software development and growth agency. We build AI agents on Claude for businesses whose work arrives as messy text: an enquiry that needs qualifying, a supplier invoice in an odd layout, a support message that could belong to three teams. Anthropic's engineering guide separates two kinds of system. Workflows are orchestrated through predefined code paths. In agents, the model dynamically directs its own process and tool use. Both are useful, and the guide advises starting with the simplest solution and adding complexity only when it pays off.
That advice is how we scope. An agent costs more to run and to test than a fixed workflow, and it can compound its own mistakes across steps, so we use one only when the number of steps cannot be written down in advance. Everything else gets a rule-based flow, a single model call, or a script.
Where the three approaches fit. Use the table to see which one your problem needs before you read further.
| Approach | How it decides | Best for | Main risk |
|---|---|---|---|
| Rule-based workflow | Fixed steps and conditions you define | Predictable work between systems with APIs | Breaks on input nobody planned for |
| Single model step inside a workflow | Rules decide the path, the model reads or classifies one input | Sorting, extracting and summarising text | A wrong label passes silently without a review rule |
| AI agent | The model chooses the next step and the tool to use | Open-ended jobs where the steps depend on what it finds | Cost, latency and compounding errors without limits |
Agents and Tools We Build for Businesses
Each build starts with one job written down step by step, and one person who owns the result.
Lead intake and qualification agents
An agent reads a new enquiry, checks your CRM for an existing contact, scores it against your qualification rules, drafts a reply and hands the lead to the right person. A team member approves anything that is sent to the prospect.
LeadsSupport triage
Incoming messages are read, tagged, routed to the right queue and given a draft answer from your own help content, with unclear cases sent to a person.
TriageDocument and invoice handling
Fields pulled from invoices, contracts and forms, checked against your records and filed, with mismatches queued for review.
DocsReporting and data clean-up
Weekly summaries written from the numbers in your systems, and duplicate or inconsistent records found, explained and fixed in batches you approve before anything is overwritten.
ReportsInternal tools built with Claude Code
Admin panels, import scripts, dashboards and small integrations built, where it fits, with Claude Code, then reviewed, tested and handed over as ordinary code your own developers can read.
ToolsMCP integrations
Connections that let an agent read from and act in your CRM, email, accounting tool or database through one standard interface, with permissions set per tool. Where no connector exists, we build one on top of your APIs.
MCPClaude Code, CLAUDE.md, MCP and Skills in Plain Terms
Anthropic describes Claude Code as an agentic coding tool that reads your codebase, edits files, runs commands and integrates with your development tools. We use it as a fast pair of hands on internal tools, scripts and integrations. It does not replace review: a developer of ours reads and tests what it produces before it is handed to you.
The table lists the pieces that matter for a business project, with what Anthropic's documentation says each one is and what it means in your build.
| Piece | What the documentation says | What it means for your project |
|---|---|---|
| CLAUDE.md | A markdown file in the project root that Claude Code reads at the start of every session, for standards, decisions and checklists | Your company's rules are written once and applied every run, and you can read and edit them |
| MCP | An open standard for connecting AI applications to external data sources, tools and workflows | One consistent way for an agent to reach your CRM, mail, accounting and database |
| Skills | Packaged repeatable workflows a team can share, such as a review or deploy routine | A routine your team repeats becomes a named, reusable step |
| Hooks | Shell commands that run before or after Claude Code actions | Checks such as formatting or linting run automatically around the agent's work |
| Subagents | Multiple agents working on parts of a task, with a lead agent coordinating and merging results | A larger job can be split, but only when the extra moving parts are worth it |
| Agent SDK | A toolkit for building custom agents with control over orchestration, tool access and permissions | The route for an agent that runs inside your own product or back office |
Claude Code can also be scripted from the command line and run on a schedule, which is how recurring checks and reports get built. The Claude Code for business automation guide shows what that looks like day to day, and the CLAUDE.md file explained post walks through what goes in the file. For the connection layer, read how MCP connects Claude to business tools.
From First Agent
to Handover
You see the agent working on test data every week before it touches live records.
Scope one first agent
We pick a single job that repeats often, with a clear definition of a good result. After a short call we send a proposal for that first piece, not for a programme.
Set up accounts in your name
Model, hosting and tool accounts are created under your company, and the agent gets its own narrow credentials. We sign an NDA first if you want one.
Write the rules down
Your policies, tone and limits go into a CLAUDE.md file and project instructions. You review them in plain language, so the rules are yours, not ours.
Build on staging, demo weekly
The agent runs on a staging copy with test data. Each week you watch it work, and we change the rules and tools from what you see.
Add approval points and logs
Sending, paying, deleting and editing customer records wait for a person. Every run is logged so you can see what the agent read, which tool it used and what it decided.
Hand over or keep it running
You receive the code, instructions, accounts and a short runbook. We can keep running and improving the agent, or your team takes over, whichever you prefer.
How We Keep an Agent Inside Its Limits
Anthropic's guide recommends extensive testing in sandboxed environments along with appropriate guardrails, and suggests agents pause for human feedback at checkpoints or when they hit a blocker. It also suggests stopping conditions such as a maximum number of iterations. We build those ideas into every agent as concrete settings you can read.
| Guardrail | What we do | Why it matters |
|---|---|---|
| Least privilege | Each agent gets only the tools and records its job needs, with read-only access first | An agent that cannot delete a record cannot delete one by mistake |
| Separate credentials | A dedicated login for the agent, never a staff member's account | Actions are attributable and the access can be revoked in one step |
| Approval points | Anything sent, paid, deleted or hard to undo waits for a named person | The decision that carries risk stays with someone accountable |
| Limits on a run | A cap on steps, time and spend, then the run stops and reports | A confused agent cannot loop for hours or run up a bill |
| Review of output | Sample checks of finished work, and a human read of anything customer-facing at first | Quality problems show up while the volume is still small |
| Error handling | Failed steps are retried by rule, then queued with an alert to a named person | Nothing fails quietly |
| Staging first | New rules and tools are tested on copies of your data before live use | A bad change is found before a customer sees it |
The same guide puts care into tool design as well: clear tool descriptions, defined edge cases and tools built so mistakes are harder to make. We apply that to the tools we give an agent, for example by making a tool accept only the record types it should touch. For process-level reliability such as retries and alerts, the workflow automation page covers the platform side.
When an Agent Is the Wrong Answer
We tell you when something simpler will do. These are the usual cases.
If you can write the whole process as fixed rules, a workflow is cheaper, faster and easier to test. Add a model only for the one step that reads text.
Payments, legal commitments and anything hard to reverse should not be left to an agent. It can prepare the case, and a person decides.
An agent working from duplicate, outdated records produces confident wrong answers. Clean-up comes first, and it can be the first project.
Ten tasks a month rarely repay the build and the testing. A checklist or a saved template does the job.
Someone has to read the alerts, approve the actions and decide when the rules change. Without that person, an agent drifts.
How This Differs From Our AI and Workflow Pages
| Page | Start here if | What it covers |
|---|---|---|
| AI and automation | You want to find and automate repetitive processes with models and rules | Process audit, document processing, chatbots and predictive work |
| Workflow automation | The steps are known and need to run reliably between systems | Triggers, approvals, syncs, alerts and run logs on Make, GoHighLevel or code |
| AI agents (this page) | The work depends on reading context and choosing the next step | Claude agents with tools, Claude Code builds, CLAUDE.md rules and MCP connections |
If you are unsure which applies, a short call is enough to sort it out. Not every project needs an agent, and some need a custom build instead of a platform, which is what our custom software development service is for. Weighing a build against doing it in-house is covered in DIY or hire an AI automation team.
For a wider look at the options, read what AI agents can automate for a business and how to automate your business with Claude.
Related Work We Have Already Delivered
Claude inside an approved workflow. In our Make lead intake automation, a single Make scenario maps a 112-field Typeform submission into GoHighLevel and Airtable, generates a business document with Claude AI, and holds delivery until a team member approves it in Slack. That is the pattern we use for agents: a model does the drafting, and a person holds the release.
A multi-agent system with manual review. The credit repair automation platform runs a 17-agent AI analysis system that flags high-risk cases for manual review.
Rules that gate a sales process. The GoHighLevel lead qualification build is rule-based, not agent-based. We list it because most agent projects begin with the same qualification rules.
We do not publish results figures for these builds beyond what each case study states, and none is a promise about what yours will do. You can browse all of it on the work page.
Platforms &
Tools
We choose per project. Tell us your stack and we will work with it.
Where the Tool Facts Come From
Statements on this page about Claude Code, CLAUDE.md, MCP, skills, hooks, subagents and the Agent SDK come from the documentation below, opened in November 2026. Tools change quickly, so check the linked page before you rely on a detail.
- Claude Code overview: what it does, CLAUDE.md, skills, hooks, subagents, Agent SDK
- Building effective agents: workflows versus agents, checkpoints, stopping conditions, tool design
- Model Context Protocol: the open standard for connecting AI applications to external systems
Case Studies
Make and Claude AI Lead Intake Automation AI Credit Repair and Automation Platform GoHighLevel Lead Qualification Automation All Case StudiesRelated Reading
AI and Automation Services Workflow Automation API Development and Integration Custom Software Development Claude Code for Business Automation The CLAUDE.md File Explained AI Agents for Business: What They Can Automate How to Automate Your Business With Claude MCP: Connect Claude to Business Tools DIY or Hire an AI Automation TeamStraight
Answers.
Plain answers to what we are asked before an agent is built.
Tell Us About Your First Agent.
Describe the job you want off your team's desk. We will say whether an agent, a workflow or a simple script fits, and quote it after a short call.
- 30-minute consultation
- NDA signed on request
- Reply within 24 hours
- Book a call30 minutes, no pitch. Tell us what you want to build.
- Get a straight answerHonest feedback on fit, scope and timeline.
- Decide with no pressureMove ahead only if it feels right. No commitment required.